Identifying Child Mental Health and Neurodevelopmental Conditions Using Real-world Clinical Data: Considerations for Mental Health Care Quality-View Presentation

Video Transcription

Video Summary

In the session titled "Identifying Child Mental Health and Neurodevelopmental Conditions Using Real-World Clinical Data," a group of experts, including Dr. Juliet Edgcomb, Dr. Nicole Benson, and Dr. Amber Ongle, explored the potential of clinical data in improving the diagnosis and care for children with mental health issues. The main objectives discussed included evaluating commonly used methods for detecting mental health and neurodevelopmental conditions in children and adolescents, developing practices to reduce implicit biases, and examining different types of clinical data.<br /><br />Dr. Benson discussed the use of digital health tools and their potential to improve healthcare delivery and outcomes through early intervention, treatment engagement, and recovery monitoring. She presented case studies on identifying schizophrenia in children using insurance claims and questioned the sufficiency of 12-month data windows to accurately identify new diagnoses, suggesting longer data histories might be necessary. The limitations and implications of using existing data sources for accurate diagnosis were also highlighted.<br /><br />Dr. Edgcomb focused on detecting self-injurious thoughts and behaviors using electronic health record (EHR) data. She examined the efficacy of ICD codes and chief complaints in identifying suicide-related behaviors, finding issues in sensitivity particularly in detecting cases among male, preteen, and minority populations. Machine learning models were introduced as a potential method to improve detection.<br /><br />Dr. Ongle's research aimed at improving the identification of autism in underserved populations, particularly girls and Latino children, using machine learning on real-world data. The importance of developing unbiased models that consider cultural and gender differences in symptom presentation was emphasized.<br /><br />The session underscored the significant potential of using real-world data to enhance identification and care for children with mental health and neurodevelopmental conditions while acknowledging the challenges and limitations in ensuring accurate and equitable diagnosis and treatment.

Keywords

Child Mental Health

Neurodevelopmental Conditions

Real-World Clinical Data

Digital Health Tools

Early Intervention

Electronic Health Records

Machine Learning

Implicit Biases

Autism Identification

Schizophrenia Diagnosis

Self-Injurious Behaviors

Cultural and Gender Differences